ERDES: A Benchmark Video Dataset for Retinal Detachment and Macular Status Classification in Ocular Ultrasound

TL;DR

Eye Retinal DEtachment ultraSound (ERDES) is introduced, the first open-access dataset of ocular ultrasound clips labeled for the presence of RD and macula-detached vs. macula-intact status, which enables machine learning development for RD detection.

Abstract

Retinal detachment (RD) is a vision-threatening condition that requires prompt intervention to preserve sight. A critical factor in treatment urgency and visual prognosis is macular involvement -- whether the macula is intact or detached. Point-of-care ultrasound (POCUS) is a fast, non-invasive and cost-effective imaging tool commonly used to detect RD in various clinical settings. However, its diagnostic utility is limited by the need for expert interpretation, especially in resource-limited environments. Deep learning has the potential to automate RD detection on ultrasound, but there are no clinically available models, and prior research has not addressed macular status -- an essential distinction for surgical prioritization. Additionally, no public dataset currently supports macular-based RD classification using ultrasound video. We introduce Eye Retinal DEtachment ultraSound (ERDES), the first open-access dataset of ocular ultrasound clips labeled for (i) presence of RD and (ii) macula-detached vs. macula-intact status. ERDES enables machine learning development for RD detection. We also provide baseline benchmarks by training 40 models across eight architectures, including 3D convolutional networks and transformer-based models.

Figures (6)

• Figure 1: Illustration of ocular globe, peripheral soft tissue and device-generated text overlays.
• Figure 2: Examples of ocular ultrasound frames with the globe (a) centered and (b) near the image boundary.
• Figure 3: Comparison of the example validation batch labels and predictions after YOLOv8 training.
• Figure 4: Summary statistics for the ERDES dataset: (a) number of frames per clip and (b) FPS values across all videos.
• Figure 5: Folder hierarchy of the ERDES dataset.